© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 145207
    Prev
    Next
    INDEX
    Explanations

    file menu actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     नीचे
    0.54
    sortBy
    0.52
    cliffe
    0.49
     Byron
    0.49
     arrondie
    0.49
    
    0.48
     görür
    0.47
     yǔ
    0.47
    бири
    0.47
    bitwise
    0.47
    POSITIVE LOGITS
    的
    0.58
     Geträn
    0.49
    來源
    0.48
     banking
    0.46
     čet
    0.46
    ın
    0.46
    ž
    0.46
    <0x0D>
    0.46
    博物館
    0.45
    čen
    0.44
    Activations Density 0.003%

    No Known Activations